Home > Research > Publications & Outputs > Modelling cognitive development with constructi...
View graph of relations

Modelling cognitive development with constructivist neural networks

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Published

Standard

Modelling cognitive development with constructivist neural networks. / Westermann, G .

Connectionist models of learning, development and evolution. ed. / Robert M. French; Jacques P. Sougne. Godalming : Springer Verlag London Ltd, 2000. p. 123-132.

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Harvard

Westermann, G 2000, Modelling cognitive development with constructivist neural networks. in RM French & JP Sougne (eds), Connectionist models of learning, development and evolution. Springer Verlag London Ltd, Godalming, pp. 123-132, 6th Neural Computation and Psychology Workshop, LIEGE, 16/09/00.

APA

Westermann, G. (2000). Modelling cognitive development with constructivist neural networks. In R. M. French, & J. P. Sougne (Eds.), Connectionist models of learning, development and evolution (pp. 123-132). Springer Verlag London Ltd.

Vancouver

Westermann G. Modelling cognitive development with constructivist neural networks. In French RM, Sougne JP, editors, Connectionist models of learning, development and evolution. Godalming: Springer Verlag London Ltd. 2000. p. 123-132

Author

Westermann, G . / Modelling cognitive development with constructivist neural networks. Connectionist models of learning, development and evolution. editor / Robert M. French ; Jacques P. Sougne. Godalming : Springer Verlag London Ltd, 2000. pp. 123-132

Bibtex

@inproceedings{c58f85ba32254953a928156c4892ae42,
title = "Modelling cognitive development with constructivist neural networks",
abstract = "Based on recent evidence from cognitive developmental neuroscience, I argue for the importance of constructivist models of cognitive developmental phenomena. This point is empirically investigated with a constructivist neural network model of the acquisition of past tense/participle inflections. The model dynamically adapts its architecture to the learning task by growing units and connections in a task-specific way during learning. In contrast to other, fixed-architecture models, the constructivist network displays a realistic, U-shaped learning behaviour. In the trained network, realistic {"}adult{"} representations emerge that lead to aphasia-like dissociations between regular and irregular forms when the model is lesioned. These results show that constructivist neural networks form valid models of cognitive developmental processes and that they avoid many of the problems of fixed-architecture models.",
keywords = "GERMAN INFLECTION, LANGUAGE, MORPHOLOGY, CORTEX, RULES",
author = "G Westermann",
year = "2000",
language = "English",
isbn = "1-85233-354-5",
pages = "123--132",
editor = "French, {Robert M.} and Sougne, {Jacques P.}",
booktitle = "Connectionist models of learning, development and evolution",
publisher = "Springer Verlag London Ltd",
note = "6th Neural Computation and Psychology Workshop ; Conference date: 16-09-2000 Through 18-09-2000",

}

RIS

TY - GEN

T1 - Modelling cognitive development with constructivist neural networks

AU - Westermann, G

PY - 2000

Y1 - 2000

N2 - Based on recent evidence from cognitive developmental neuroscience, I argue for the importance of constructivist models of cognitive developmental phenomena. This point is empirically investigated with a constructivist neural network model of the acquisition of past tense/participle inflections. The model dynamically adapts its architecture to the learning task by growing units and connections in a task-specific way during learning. In contrast to other, fixed-architecture models, the constructivist network displays a realistic, U-shaped learning behaviour. In the trained network, realistic "adult" representations emerge that lead to aphasia-like dissociations between regular and irregular forms when the model is lesioned. These results show that constructivist neural networks form valid models of cognitive developmental processes and that they avoid many of the problems of fixed-architecture models.

AB - Based on recent evidence from cognitive developmental neuroscience, I argue for the importance of constructivist models of cognitive developmental phenomena. This point is empirically investigated with a constructivist neural network model of the acquisition of past tense/participle inflections. The model dynamically adapts its architecture to the learning task by growing units and connections in a task-specific way during learning. In contrast to other, fixed-architecture models, the constructivist network displays a realistic, U-shaped learning behaviour. In the trained network, realistic "adult" representations emerge that lead to aphasia-like dissociations between regular and irregular forms when the model is lesioned. These results show that constructivist neural networks form valid models of cognitive developmental processes and that they avoid many of the problems of fixed-architecture models.

KW - GERMAN INFLECTION

KW - LANGUAGE

KW - MORPHOLOGY

KW - CORTEX

KW - RULES

M3 - Conference contribution/Paper

SN - 1-85233-354-5

SP - 123

EP - 132

BT - Connectionist models of learning, development and evolution

A2 - French, Robert M.

A2 - Sougne, Jacques P.

PB - Springer Verlag London Ltd

CY - Godalming

T2 - 6th Neural Computation and Psychology Workshop

Y2 - 16 September 2000 through 18 September 2000

ER -